© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34464
    Prev
    Next
    INDEX
    Explanations

    neither the name of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verter
    -0.09
    .Unsupported
    -0.09
    MBED
    -0.09
    ãĤ¡
    -0.09
    manship
    -0.09
    ucci
    -0.09
    leigh
    -0.08
    sus
    -0.08
    .Flag
    -0.08
    uxtap
    -0.08
    POSITIVE LOGITS
    theless
    0.16
    hood
    0.10
    使çĶ¨èĢħæĪĸ
    0.09
     highs
    0.09
    oft
    0.09
    -than
    0.09
    istic
    0.09
     ë¶Ī구íķĺê³ł
    0.08
     Voll
    0.08
    ä¹ŁæĹłæ³ķ
    0.08
    Activations Density 0.010%

    No Known Activations